Papers › OpenVLA: An Open-Source Vision-Language-Action Model

OpenVLA: An Open-Source Vision-Language-Action Model

13 Jun 2024arXiv:2406.09246archive 2025-07-28

Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti, Ted Xiao, Ashwin Balakrishna, Suraj Nair, Rafael Rafailov, Ethan Foster, Grace Lam, Pannag Sanketi, Quan Vuong, Thomas Kollar, Benjamin Burchfiel, Russ Tedrake, Dorsa Sadigh, Sergey Levine, Percy Liang, Chelsea Finn

Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vision-language-action (VLA) models to obtain robust, generalizable policies for visuomotor control. Yet, widespread adoption of VLAs for robotics has been challenging as 1) existing VLAs are largely closed and inaccessible to the public, and 2) prior work fails to explore methods for efficiently fine-tuning VLAs for new tasks, a key component for adoption. Addressing these challenges, we introduce OpenVLA, a 7B-parameter open-source VLA trained on a diverse collection of 970k real-world robot demonstrations. OpenVLA builds on a Llama 2 language model combined with a visual encoder that fuses pretrained features from DINOv2 and SigLIP. As a product of the added data diversity and new model components, OpenVLA demonstrates strong results for generalist manipulation, outperforming closed models such as RT-2-X (55B) by 16.5% in absolute task success rate across 29 tasks and multiple robot embodiments, with 7x fewer parameters. We further show that we can effectively fine-tune OpenVLA for new settings, with especially strong generalization results in multi-task environments involving multiple objects and strong language grounding abilities, and outperform expressive from-scratch imitation learning methods such as Diffusion Policy by 20.4%. We also explore compute efficiency; as a separate contribution, we show that OpenVLA can be fine-tuned on consumer GPUs via modern low-rank adaptation methods and served efficiently via quantization without a hit to downstream success rate. Finally, we release model checkpoints, fine-tuning notebooks, and our PyTorch codebase with built-in support for training VLAs at scale on Open X-Embodiment datasets.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 3 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 10 samples from 3 repositories, 8 ran (7 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

openvla/openvla mentioned on GitHubpytorchMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
pie33000/OpenVLA mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
stanford-iliad/openvla-mini mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
6ran
2unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

openvla/openvla community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
crop_and_resize in 11 papers experiments/robot/openvla_utils.py ran MIT (permissive) · d4883358a40b04e4 · report fixture: signature image:EagerTensor/3/float, crop_scale:float/0/float, batch_size:int/0/int · returned EagerTensor · level recorded 2026-09-24
get_image_resize_size experiments/robot/robot_utils.py ran · honoured contract MIT (permissive) · 01fa10b1e4f2b232 · report fixture: signature cfg:Config/0/? · returned int · level recorded 2026-09-24
get_openvla_prompt vla-scripts/deploy.py unverified MIT (permissive) · 5dcd468341e1592d · report
get_processor in 5 papers experiments/robot/openvla_utils.py unverified MIT (permissive) · 886ca388dfb17143 · report
pie33000/OpenVLA community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
parse_stanford_hydra_dataset convert_tf_to_numpy.py ran MIT (permissive) · 81047a80f05792ed · report fixture: signature step:dict/0/? · returned tuple · level recorded 2026-09-24
parse_viola_dataset convert_tf_to_numpy.py ran MIT (permissive) · 6595ff27135d42d4 · report fixture: signature step:dict/0/? · returned tuple · level recorded 2026-09-24
stanford-iliad/openvla-mini community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
get_openvla_prompt vla-scripts/extern/verify_openvla.py ran · our draft was wrong fingerprinted MIT (permissive) · 883da746d4398ec2 · report fixture: signature instruction:str/0/str · returned str · level recorded 2026-09-26
hr_name experiments/robot/robot_utils.py ran fingerprinted MIT (permissive) · ef2c04230ed3e692 · report fixture: signature float_arg:float/0/float, fp:int/0/int · returned str · level recorded 2026-09-24
remap_state_dicts_for_hf vla-scripts/extern/convert_openvla_weights_to_hf.py ran MIT (permissive) · 7af07bf1a8a753fe · report fixture: signature prismatic_vision_backbone_state_dict:dict/0/?, projector_state_dict:dict/0/?, llm_backbone_state_dict:dict/0/?, use_fused_vision_backbone:bool/0/bool · returned dict · level recorded 2026-09-26
round_to_n experiments/robot/robot_utils.py ran fingerprinted MIT (permissive) · a6a8431fbd02a85e · report fixture: signature x:float/0/float, n:int/0/int · returned float · level recorded 2026-09-25

Tasks

Imitation LearningLanguage ModellingQuantizationRobot ManipulationVision-Language-Actionmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Robot Manipulation CALVIN OpenVLA avg. sequence length (D to D) 3.27 #13 of 19 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot OpenVLA Variant Aggregation 0.411 #8 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot OpenVLA Variant Aggregation-Move Near 0.477 #8 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot OpenVLA Variant Aggregation-Open/Close Drawer 0.177 #8 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot OpenVLA Variant Aggregation-Pick Coke Can 0.545 #8 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot OpenVLA Visual Matching 0.277 #8 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot OpenVLA Visual Matching-Move Near 0.462 #8 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot OpenVLA Visual Matching-Open/Close Drawer 0.356 #8 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot OpenVLA Visual Matching-Pick Coke Can 0.163 #8 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X OpenVLA Average 0.010 #7 of 7 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X OpenVLA Put Carrot on Plate 0.000 #7 of 7 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X OpenVLA Put Spoon on Towel 0.000 #7 of 7 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X OpenVLA Stack Green Block on Yellow Block 0.000 #7 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

DiffusionLLaMA

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections